當使用 test 開頭的 command、skill、agent 時,在執行過程中使用者提出改善建議,立即調整 .claude 目錄中對應的 md 檔案
當測試 test 開頭的 plugin 時,使用者提出改善建議,會立即定位並修改 `.claude` 目錄中對應的 md 檔案。能快速修正 agent、command 或 skill 的內容,並提供修改前後對比說明。
/plugin marketplace add MilesChou/claude-marketplace/plugin install plugin-dev@mileschou-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
當使用 test 開頭的 command、skill、agent 進行測試時,若使用者提出改善建議,立即定位並調整 .claude 目錄中對應的 md 檔案。
當使用者在測試過程中提出改善觀點時:
識別目標 Plugin
定位目標檔案
plugins/{plugin-name}/agents/{agent-name}.mdplugins/{plugin-name}/commands/{command-name}.mdplugins/{plugin-name}/skills/{skill-name}/SKILL.md使用 Read tool 讀取目標檔案
Read: plugins/{plugin-name}/{type}/{name}/檔案.md
分析使用者的改善觀點
確認修改範圍
使用 Edit tool 進行修改
注意事項
多處修改
重新讀取檔案
向使用者說明修改內容
詢問是否需要繼續測試
測試 Agent 時
測試 Command 時
測試 Skill 時
[使用者正在測試某個 skill]
User: 我發現這個 skill 的步驟 3 說明不夠清楚,
應該要先執行 git status 再決定要用哪個策略。
Agent: 我會立即修正這個 skill 的 SKILL.md 檔案。
[使用 Read tool 讀取當前的 SKILL.md]
[使用 Edit tool 修改步驟 3 的內容]
Agent: 已修改 plugins/git/skills/resolving-conflict/SKILL.md:42
- 在步驟 3 開頭新增「先執行 git status 確認狀態」的說明
- 補充不同狀態下的處理策略
修改內容:
原本:「對於每個衝突的檔案...」
修改後:「先執行 git status 確認衝突狀態,再對於每個衝突的檔案...」
你要繼續測試看看嗎?
User: 好的,再測試一次。
[繼續測試流程...]
如果需要修改 YAML Front Matter(name 或 description):
---
name: 原始名稱
description: 原始描述
---
修改時要特別注意:
--- 分隔線的完整性如果使用者的改善意見需要大幅度重構:
使用 AskUserQuestion 確認範圍
分步驟進行
保持溝通
如果改善意見涉及多個檔案(例如 SKILL.md 和 README.md):
使用 TodoWrite 規劃任務
按順序執行
整體確認
避免:
推薦:
修改完成後檢查:
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.